Autonomous AI agents that perform tasks independently
david.burley
Persistent memory framework for AI agents — fact extraction, hybrid retrieval, context management, and persona identity
caopeng
Measures structural type safety and boundary validation to reduce fallback cascades for AI agents
amersarhan
A blazing-fast AI coding agent for your terminal
Secure your LangChain agents with per-agent identity, policy enforcement, and tamper-proof audit logs.
duncanndegwa
DevFortress SDK — API and application security with automated threat response, session privacy, and AI agent observability.
...moreA lightweight, production-ready AI security SDK for protecting LLM agents.
zero-nium
ElizaOS plugin for Project Substitute Arena — counterfactual CEO simulation (Toys R Us 2006-2017)
alifaleh
Self-evolving R&D framework for Claude Code. Claude becomes an autonomous scientist who owns the project, researches deeply, builds knowledge, and never stops learning.
...moremy_name_is_yu
AI agent orchestrator that gives existing agents the drive to persist — set a goal, and PulSeed observes, delegates, verifies, and loops until done.
...moreArthas Zeng
Cursor-native multi-agent development framework with 5-role review
Manage and sync AI agent skills across Claude Code, Cursor, Windsurf, and Codex
Jon Maccarello & Claw-ED contributors
Your AI co-teacher. Generate lessons, games, slides, and assessments from your terminal. Learns your teaching voice, aligns to your state standards, and works with any LLM provider.
...moreGitHub Actions
Browser automation for AI agents. Single binary, zero dependencies, CDP direct.
FastAIFoundry <[email protected]>
Build, debug, evaluate, and operate AI agents. The only SDK with fork-and-rerun Agent Replay.
Tarcísio Junior <[email protected]>
Time completo de desenvolvimento autônomo por IA
EngramX — The open-source agent memory framework with pluggable storage, lifecycle policies, observability, and framework adapters.
...moreFilesystem-first harness optimization for coding agents.
Leap0 sandbox integration for Deep Agents
HireSquire LangChain Tools - AI-powered candidate screening for agents
Multi-agent debate framework with structured consensus scoring and dissent tracking
Minimal AI coding agent (~1300 LoC) inspired by Claude Code. Works with any LLM.
Universal coding agent for your terminal — use any OpenAI-compatible LLM
Fleet Command dashboard for Claude Code — track agents, missions, and progress with a galaxy map visualization
TurboQuant-powered agentic AI framework for long-context LLMs on consumer hardware